Explore the concept of self-play in artificial intelligence through a 56-minute lecture delivered by Noam Brown at the 2024 Cooperative AI Summer School. Delve into the expertise of this renowned OpenAI researcher, known for his groundbreaking work in multi-agent AI and imperfect-information games. Gain insights from the co-creator of Libratus and Pluribus, the first AIs to defeat top human players in two-player and multiplayer no-limit poker. Learn from Brown's distinguished career, which includes accolades such as the Marvin Minsky Medal for Outstanding Achievements in AI and recognition as one of MIT Tech Review's 35 Innovators Under 35. Discover how his work on Pluribus was acknowledged as one of the top 10 scientific breakthroughs by Science Magazine. Benefit from the knowledge of this Carnegie Mellon University PhD graduate, recipient of the School of Computer Science Distinguished Dissertation Award, as he shares his expertise on self-play techniques in AI development.
Overview
Syllabus
Self-Play by Noam Brown
Taught by
Cooperative AI Foundation
Related Courses
-
Learning to Cooperate and Compete via Self Play
-
Multi-Agent Dynamics with Self-Play Reinforcement Learning
-
The Role of Multi-Agent Learning in Artificial Intelligence Research at DeepMind
-
ReBeL - Combining Deep Reinforcement Learning and Search for Imperfect-Information Games
-
Independent Learning Dynamics for Stochastic Games - Where Game Theory Meets
-
Multi-Agent Reinforcement Learning - Part I
